Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark this as destructiveHint=true and readOnlyHint=false. The description adds meaningful context beyond annotations by stating 'No Meta write' and specifying that it only discards a locally prepared update, which clarifies the destructive scope.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tightly packed sentences: the first defines the action and required input, the second gives alternatives. No redundant wording or repetition of schema/annotation data.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one required string, output schema present), the description covers purpose, token semantics, behavioral scope, and alternatives. Nothing essential is missing for an agent to select and invoke this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema contains one undocumented string parameter (confirm_token), so the description carries the full burden. It explains that the token must be exact and follow the bu_confirm_* or mu_confirm_* pattern, which is valuable but does not specify where the token originates.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Discard') applied to a specific resource ('a prepared status, campaign/ad-set budget or bid update') and identifies the exact token required. It also differentiates this tool from nearby siblings by naming launch_deny and products_delivery_pause_deny for adjacent cases.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit routing guidance: use launch_deny for creation/copy drafts and products_delivery_pause_deny for product-family pauses. It also clarifies that this tool performs no Meta write, helping the agent avoid it when a real external write is needed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.